Answers are grounded in this paper and cite their sources.
Lhoksukon District in North Aceh Regency is a lowland area that is prone to annual flooding due to the overflowing Keureutoe River and Pasee River. The lack of an adequate digital mapping management system at the North Aceh Regional Disaster Management Agency (BPBD) causes the process of identifying the level of vulnerability to be carried out semi-manually. This study aims to conduct clustering analysis in mapping and detect the distribution pattern of flood-prone areas in Lhoksukon District using historical data from 2018 to 2025. The method used is the Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to group areas based on object distance density without requiring initial determination of the number of clusters. In addition, this study applies Spatial Pattern Analysis to detect spatial autocorrelation and Flexibly Shaped Spatial Scan Statistics to identify cluster distribution patterns that have irregular shapes. The analysis was carried out using QGIS software and Python programming with a village-level analysis scale (micro-level). The results of the study show that the DBSCAN algorithm consistently forms three main groups: Cluster 0 as the dominant group with homogeneous soil physical characteristics, Cluster 1 and 2 as secondary groups, and the Noise category (red dots) for villages with extreme physical anomalies such as Mata Ie and Buket Krueng Villages. Temporal controller visualization shows the dynamics of cluster changes in several villages that indicate changes in land function over time. The resulting risk zoning map is expected to be a strategic reference for the BPBD of North Aceh Regency in planning mitigation and early warning systems for flood disasters.
No takes yet. Share an insight, caveat, or question.
AR et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: